mm/zswap: invalidate zswap entry when swap entry free

During testing I found there are some times the zswap_writeback_entry()
return -ENOMEM, which is not we expected:

bpftrace -e 'kr:zswap_writeback_entry {@[(int32)retval]=count()}'
@[-12]: 1563
@[0]: 277221

The reason is that __read_swap_cache_async() return NULL because
swapcache_prepare() failed.  The reason is that we won't invalidate zswap
entry when swap entry freed to the per-cpu pool, these zswap entries are
still on the zswap tree and lru list.

This patch moves the invalidation ahead to when swap entry freed to the
per-cpu pool, since there is no any benefit to leave trashy zswap entry on
the tree and lru list.

With this patch:
bpftrace -e 'kr:zswap_writeback_entry {@[(int32)retval]=count()}'
@[0]: 259744

Note: large folio can't have zswap entry for now, so don't bother
to add zswap entry invalidation in the large folio swap free path.

Link: https://lkml.kernel.org/r/20240201-b4-zswap-invalidate-entry-v2-2-99d4084260a0@bytedance.com
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/zswap.h b/include/linux/zswap.h
index 91895ce1fdbc4f89a5d337e86cc0314548e98afe..341aea4900704ce29159e0c2a53a0416b9f1a2ed 100644 (file)
--- a/include/linux/zswap.h
+++ b/include/linux/zswap.h
@@ -29,7 +29,7 @@ struct zswap_lruvec_state {
 
 bool zswap_store(struct folio *folio);
 bool zswap_load(struct folio *folio);
-void zswap_invalidate(int type, pgoff_t offset);
+void zswap_invalidate(swp_entry_t swp);
 int zswap_swapon(int type, unsigned long nr_pages);
 void zswap_swapoff(int type);
 void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg);
@@ -50,7 +50,7 @@ static inline bool zswap_load(struct folio *folio)
        return false;
 }
 
-static inline void zswap_invalidate(int type, pgoff_t offset) {}
+static inline void zswap_invalidate(swp_entry_t swp) {}
 static inline int zswap_swapon(int type, unsigned long nr_pages)
 {
        return 0;

diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 0bec1f705f8e09313e1fcdcf87568cd5bf68da38..90973ce7881db2a65c38d21b7b2fad28e60ade36 100644 (file)
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -273,6 +273,9 @@ void free_swap_slot(swp_entry_t entry)
 {
        struct swap_slots_cache *cache;
 
+       /* Large folio swap slot is not covered. */
+       zswap_invalidate(entry);
+
        cache = raw_cpu_ptr(&swp_slots);
        if (likely(use_swap_slot_cache && cache->slots_ret)) {
                spin_lock_irq(&cache->free_lock);

diff --git a/mm/swapfile.c b/mm/swapfile.c
index a8edaf4e5b8ad94f4f594ba7d1dcd201072e44af..d1bd8d1e17bd3057c05f2626da00b37f11dbc866 100644 (file)
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -744,7 +744,6 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
                swap_slot_free_notify = NULL;
        while (offset <= end) {
                arch_swap_invalidate_page(si->type, offset);
-               zswap_invalidate(si->type, offset);
                if (swap_slot_free_notify)
                        swap_slot_free_notify(si->bdev, offset);
                offset++;

diff --git a/mm/zswap.c b/mm/zswap.c
index 35da20d3617fece6ec5ca230ecd3866c7cf4bff4..ef41a7bd81f243ce2514dbd3346c46933f2b904c 100644 (file)
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1739,9 +1739,10 @@ bool zswap_load(struct folio *folio)
        return true;
 }
 
-void zswap_invalidate(int type, pgoff_t offset)
+void zswap_invalidate(swp_entry_t swp)
 {
-       struct zswap_tree *tree = swap_zswap_tree(swp_entry(type, offset));
+       pgoff_t offset = swp_offset(swp);
+       struct zswap_tree *tree = swap_zswap_tree(swp);
        struct zswap_entry *entry;
 
        spin_lock(&tree->lock);